© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 84280
    Prev
    Next
    INDEX
    Explanations

    comments, moderation, or foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -0.93
     despite
    -0.82
    <h4>
    -0.81
    నా
    -0.81
     Oprah
    -0.80
    шње
    -0.79
    <h2>
    -0.79
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.79
     malgré
    -0.76
    υνα
    -0.76
    POSITIVE LOGITS
     moderation
    1.00
     Disqus
    0.93
     образования
    0.90
    ⫹
    0.87
     triggered
    0.86
     conçus
    0.85
    Moder
    0.84
     Kartoffeln
    0.82
     Moderator
    0.82
     passim
    0.82
    Activations Density 0.019%

    No Known Activations